Iβm a graduate student in Xiβan Jiaotong University, majoring in computer science. Itβs my great honor to be mentored by Prof.Qin. Meanwhile, Iβm also so lucky to study under the guidance of Professor Jun Liu, Associate Professor Lingling Zhang, Associate Professor Jie Ma and teacher Bifan Wei.
My research interests include LLM reasoning, LLM (GUI) agent, etc. Please refer to Google Scholar for more information.
π₯ News
- 2026.02: Β ππ Our paper OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions is released on arxiv!!!
- 2026.02: Β ππ Our paper TIDE: Trajectory-based Diagnostic Evaluation of Test-Time Improvement in LLM Agents is released on arxiv!!!
- 2025.07: Β ππ Our paper MUR : Momentum Uncertainty guided Reasoning for Large Language Models is released on arxiv!!!
- 2025.05: Β ππ Our paper Ο-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation is accepted by
ACL 2025!!! - 2025.05: Β ππ Our paper Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning is accepted by
ACL 2025!!! - 2025.05: Β ππ Our paper SAGE: Scale-Aware Gradual Evolution for Continual Knowledge Graph Embedding is accepted by
KDD 2025!!! - 2024.07: Β ππ Our paper FPrompt-PLM: Flexible-Prompt on Pretrained Language Model for Continual Few-Shot Relation Extraction is published on
IEEE TKDE!!!
π Researches
OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions
Fangzhi Xu*, Hang Yan*, Qiushi Sun*, Jinyang Wu, Zixian Huang, Muye Huang, Jingyang Gong, Zichen Ding, Kanzhi Cheng, Yian Wang, Xinyu Che, Zeyi Sun, Jian Zhang, Zhangyue Yin, Haoran Luo, Xuanjing Huang, Ben Kao, Jun Liu, Qika Lin
(* means equal first)
TIDE: Trajectory-based Diagnostic Evaluation of Test-Time Improvement in LLM Agents
Hang Yan*, Xinyu Che*, Fangzhi Xu*, Qiushi Sun, Zichen Ding, Kanzhi Cheng, Jian Zhang, Tao Qin, Jun Liu, Qika Lin
(* means equal first)
MUR : Momentum Uncertainty guided Reasoning for Large Language Models
Hang Yan*, Fangzhi Xu*, Rongman Xu, Yifei Li, Jian Zhang, Haoran Luo, Xiaobo Wu, Luu Anh Tuan, Haiteng Zhao, Qika Lin, Jun Liu
(* means equal first)
Ο-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation [CCF-A]
Fangzhi Xu*, Hang Yan*, Chang Ma, Haiteng Zhao, Jun Liu, Qika Lin, Zhiyong Wu
(* means equal first)
Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning [CCF-A]
Fangzhi Xu, Hang Yan, Chang Ma, Haiteng Zhao, Qiushi Sun, Kanzhi Cheng, Junxian He, Jun Liu, Zhiyong Wu
SAGE: Scale-Aware Gradual Evolution for Continual Knowledge Graph Embedding [CCF-A]
Yifei Li, Lingling Zhang, Hang Yan, Tianzhe Zhao, Zihan Ma, Muye Huang, Jun Liu
FPrompt-PLM: Flexible-Prompt on Pretrained Language Model for Continual Few-Shot Relation Extraction [CCF-A]
Lingling Zhang , Yifei Li , Qianying Wang , Yun Wang, Hang Yan, Jiaxin Wang , Jun Liu
π Honors and Awards
- 2025.10
National scholarshipfor graduate student. - 2024.10 University scholarship for graduate student.
- 2023.10
National scholarshipfor undergraduate student. - 2022.10 University scholarship for undergraduate student.
- 2021.10 University scholarship for undergraduate student.
π Educations
- 2024.09 - (now), graduate student in Xiβan Jiaotong University, majoring computer science.
- 2020.09 - 2024.06, undergraduate student in Xiβan Jiaotong University, majoring computer science.